Allows cloning of the trading bot repository from GitHub to set up the MCP server.
Required as a runtime environment for the MCP server.
Used as a package manager to install dependencies for the MCP server.
Used as the programming language for building the trading bot project.
Offered as an alternative package manager to npm for installing dependencies.
Enables automated stock trading on the Zerodha platform, providing tools for buying and selling stocks, checking market status, retrieving real-time quotes, viewing order history and positions, monitoring account balance, and canceling orders.
Utilized for schema validation within the trading bot implementation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Zerodha Trading Bot MCP buy 10 shares of Reliance Industries"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A trading bot built using the Model Context Protocol (MCP) that provides a set of tools for automated trading operations. This bot offers various functionalities for trading stocks, managing positions, and accessing market information.
Stock Trading
Buy stocks with specified quantity
Sell stocks with specified quantity
Cancel existing orders
Market Information
Get real-time quotes for stocks
Check market status
View order history
Account Management
View current positions
Check account balance
Monitor order status
Related MCP server: Zerodha MCP Server
Node.js (Latest LTS version recommended)
npm or yarn package manager
Trading account credentials (configured in mcp-conf.json)
Clone the repository:
git clone https://github.com/AmritanshuPrashar/zerodha-mcp.git
cd mcp-zerodhaInstall dependencies:
npm installConfigure your trading credentials:
Create a mcp-conf.json file in the root directory
Add your trading platform credentials and configuration
The mcp-conf.json file should contain the following structure:
{
"buyStock": {
"prompt": "Your buy stock prompt"
},
"sellStock": {
"prompt": "Your sell stock prompt"
},
"getPosition": {
"prompt": "Your get position prompt"
},
"getMarketStatus": {
"prompt": "Your market status prompt"
},
"getQuote": {
"prompt": "Your quote prompt"
},
"getOrderHistory": {
"prompt": "Your order history prompt"
},
"cancelOrder": {
"prompt": "Your cancel order prompt"
},
"getAccountBalance": {
"prompt": "Your account balance prompt"
}
}The bot provides several tools that can be used through the MCP interface:
buy-stock: Place buy orders for stocks
sell-stock: Place sell orders for stocks
get-positions: View current positions
get-market-status: Check market status
get-quote: Get real-time quotes
get-order-history: View order history
cancel-order: Cancel existing orders
get-account-balance: Check account balance
The project is built using:
TypeScript
Model Context Protocol (MCP) SDK
Zod for schema validation
[Add your chosen license here]
Contributions are welcome! Please feel free to submit a Pull Request.
This trading bot is for educational purposes only. Use at your own risk. Always test thoroughly before using with real money.
This server cannot be deployed
AI trading bots: generate strategies, backtest, deploy live to 10+ brokers. No coding required.
Trade, monitor portfolios, and build Coinrule strategies by chat.
Automate trading on your own Alpaca account - build, backtest and run strategies via your AI.
Build, backtest, and deploy quantitative trading strategies from your AI agent.
